def extract_user_info(doc):
try:
scripts = util.extract_script(doc)
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__63"'
)
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__62"'
)
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__61"'
)
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__59"'
)
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
lis = html.xpath(r'//ul/li')
info = []
for li in lis:
text = li.xpath("string()")
info.append(util.clean_text(text))
level_info = extract_level_info(doc)
if level_info:
info.append(level_info)
return info
except:
traceback.print_exc()
return None
def extract_user_info(doc):
try:
scripts = util.extract_script(doc)
script = util.select_script(scripts,
r'"domid":"Pl_Official_PersonalInfo__63"')
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__62"')
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__61"')
if script is None:
script = util.select_script(
scripts, r'"domid":"Pl_Official_PersonalInfo__59"')
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
lis = html.xpath(r'//ul/li')
info = []
for li in lis:
text = li.xpath("string()")
info.append(util.clean_text(text))
level_info = extract_level_info(doc)
if level_info:
info.append(level_info)
return info
except:
traceback.print_exc()
return None
def extract_level_info(doc):
try:
scripts = util.extract_script(doc)
script = util.select_script(scripts,
r'"domid":"Pl_Official_RightGrowNew')
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
p = html.xpath(r'//p[@class="level_info"]')
if p:
text = p[0].xpath("string()")
info = util.clean_text(text)
return info
except:
traceback.print_exc()
return None
def extract_level_info(doc):
try:
scripts = util.extract_script(doc)
script = util.select_script(
scripts, r'"domid":"Pl_Official_RightGrowNew'
)
html = util.extract_html_from_script(script.text.strip())
html = etree.HTML(html)
p = html.xpath(r'//p[@class="level_info"]')
if p:
text = p[0].xpath("string()")
info = util.clean_text(text)
return info
except:
traceback.print_exc()
return None